Compare Start here

Google DeepMindLanguage modelSuperseded

Gemini 2.0 Flash

Fast, cheap multimodal model that powered Google's agent experiments.

Compare head-to-head Race it in 3D

Overall Intelligence

#53

of 56
29.2 pts behind #1

0

races led

201

weeks at #1

59.6

score

Released: Feb 5, 2025; 1.7 yr ago
Context: 1M; 8K max output
Price: $0.1 / $0.4; per 1M in/out · $0.18 blended
Speed: 250 tok/s; 0.4s to first token
Modalities: text · image · audio · video; outputs text
Weights: Closed; API and apps

The 30-second version

Fast, cheap multimodal model that powered Google's agent experiments.

Key takeaways

1Fast, cheap multimodal model that powered Google's agent experiments.

Where it ranks

Current snapshot · illustrative scores · click any race to watch it

2.0 FlashBest on each axis

Overall

53Overall+29.2 pts

Coding

56Coding+36.0 pts 56Frontend & UI+193 Elo 56Backend & APIs+32.6 pts 56Distributed Systems+35.8 pts 55Full-Stack Apps+32.9 pts 55Debugging & Repair+35.9 pts 55Agentic Coding+37.7 pts 55Code Review & Security+31.8 pts 56Data Science & SQL+32.8 pts 56Mobile Apps+32.2 pts 56Terminal & DevOps+42.8 pts 56Competitive Programming+1,162

Hard Reasoning

56Hard Reasoning+36.1 pts 55Frontier Questions+63.6 pts 55Abstract & Novel Reasoning+45.8 pts 56Logic & Puzzles+33.1 pts 55Planning & Strategy+34.5 pts

Math

56Math+39.0 pts 56Competition Math+29.8 pts 55Research Math+48.9 pts 56Applied & Quantitative+33.4 pts

Science

56Science+34.9 pts 56Graduate Science QA+22.0 pts 56Biology & Medicine+29.0 pts 56Physics & Chemistry+30.8 pts 56Research Assistance+31.1 pts

Writing & Language

56Writing & Language+34.4 pts 55Creative Writing+219 Elo 56Technical Writing+27.6 pts 56Editing & Style+28.2 pts 56Multilingual+22.1 pts 56Instruction Following+23.9 pts 55Conversation & EQ+188 Elo

Multimodal

37Multimodal+32.2 pts 42Image Understanding+26.4 pts 42Documents & Charts+26.8 pts 32Video Understanding+27.6 pts 30Speech & Audio+29.1 pts

Tool Use & Agents

53Tool Use & Agents+34.4 pts 56Tool Use+27.8 pts 45Computer Use+41.7 pts 56Web Research+42.2 pts 55Long-Horizon+28.3 hrs

Long Context

53Long Context+31.4 pts 531M Recall+25.1 pts 52Long Reasoning+28.9 pts

Speed & Cost

4Speed & Cost+11.1 pts 4Output Speed+273 tok/s 2Latency+0.04s 9Cost-Efficiency+30.4 pts

Trust & Factuality

56Trust & Factuality+34.5 pts 56Factuality+27.2 pts 56Honesty & Calibration+29.4 pts

Overall Intelligence over time

#1 frontier2.0 FlashV4.1 FlashGLM-5.3

Update history

The distilled version first; open any release for the deeper breakdown.

The Gemini Flash family

2.0 FlashFebruary 2025 3 FlashDecember 2025 3.5 FlashMay 2026

60-second briefing

2.0 Flash, explained

AI video summary · placeholder render from the auto-written script

From Google's own guide, distilled

Gemini prompt design strategies

Structure prompts as persona, task, context and format; the format line is the most often forgotten.
Few-shot examples set the pattern; keep their formatting identical so the model copies structure, not noise.
Gemini reads images, video and PDFs natively, so attach the source instead of describing it.
Place media before the text instruction that refers to it.
Break complex jobs into a chain of smaller prompts and pass outputs forward.

All official guides, distilled →

About Google DeepMind

Google's AI lab behind Gemini, Veo, Imagen and Nano Banana.

Optimising for

Native multimodality (image, video, audio), very long context, science, and tight integration with Search, Workspace and Android.

London, UK / Mountain View, US · founded 2010

Closest rivals

2.0 Flash is 53rd in overall intelligence; leader is Claude Opus 5.5.